Mapping and Influencing the Political Ideology of Large Language Models using Synthetic Personas

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Bernardelle, Pietro, Fröhling, Leon, Civelli, Stefano, Lunardi, Riccardo, Roitero, Kevin, Demartini, Gianluca
Format: Preprint
Veröffentlicht: 2024
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866929732171333632
author Bernardelle, Pietro
Fröhling, Leon
Civelli, Stefano
Lunardi, Riccardo
Roitero, Kevin
Demartini, Gianluca
author_facet Bernardelle, Pietro
Fröhling, Leon
Civelli, Stefano
Lunardi, Riccardo
Roitero, Kevin
Demartini, Gianluca
contents The analysis of political biases in large language models (LLMs) has primarily examined these systems as single entities with fixed viewpoints. While various methods exist for measuring such biases, the impact of persona-based prompting on LLMs' political orientation remains unexplored. In this work we leverage PersonaHub, a collection of synthetic persona descriptions, to map the political distribution of persona-based prompted LLMs using the Political Compass Test (PCT). We then examine whether these initial compass distributions can be manipulated through explicit ideological prompting towards diametrically opposed political orientations: right-authoritarian and left-libertarian. Our experiments reveal that synthetic personas predominantly cluster in the left-libertarian quadrant, with models demonstrating varying degrees of responsiveness when prompted with explicit ideological descriptors. While all models demonstrate significant shifts towards right-authoritarian positions, they exhibit more limited shifts towards left-libertarian positions, suggesting an asymmetric response to ideological manipulation that may reflect inherent biases in model training.
format Preprint
id arxiv_https___arxiv_org_abs_2412_14843
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Mapping and Influencing the Political Ideology of Large Language Models using Synthetic Personas
Bernardelle, Pietro
Fröhling, Leon
Civelli, Stefano
Lunardi, Riccardo
Roitero, Kevin
Demartini, Gianluca
Computation and Language
Artificial Intelligence
The analysis of political biases in large language models (LLMs) has primarily examined these systems as single entities with fixed viewpoints. While various methods exist for measuring such biases, the impact of persona-based prompting on LLMs' political orientation remains unexplored. In this work we leverage PersonaHub, a collection of synthetic persona descriptions, to map the political distribution of persona-based prompted LLMs using the Political Compass Test (PCT). We then examine whether these initial compass distributions can be manipulated through explicit ideological prompting towards diametrically opposed political orientations: right-authoritarian and left-libertarian. Our experiments reveal that synthetic personas predominantly cluster in the left-libertarian quadrant, with models demonstrating varying degrees of responsiveness when prompted with explicit ideological descriptors. While all models demonstrate significant shifts towards right-authoritarian positions, they exhibit more limited shifts towards left-libertarian positions, suggesting an asymmetric response to ideological manipulation that may reflect inherent biases in model training.
title Mapping and Influencing the Political Ideology of Large Language Models using Synthetic Personas
topic Computation and Language
Artificial Intelligence
url https://arxiv.org/abs/2412.14843